跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 05:44 — 2026-11-09 05:44（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 05:07最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
新论文 · v1arXiv:2610.38568HF 社区推荐

A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement

Yu Liu, Youxing Li, Yuedong Tan, Zhiwei Yang, Zihan Su, Hanqi Feng, Shaojie Zhang, Libin Liao 等 20 位作者

原文摘要

Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on what experience to generate next, while paying less attention to when fresh experience should be introduced. Many also construct training targets through self-consistency or majority voting, making supervision depend on the model's own uncertain predictions. We address these two questions separately: training dynamics determine when to acquire new experience, while the answers to new tasks remain independently checkable. A-RSI monitors reward variation and accuracy in training logs to refresh a task pool when its learning signal declines, without consulting validation or test scores. A static library of model-authored programs produces multimodal questions and derives their reference answers; we specify the task-generation contract, automatically verify chosen properties of the reward and refresh rules, and separately audit the generated answers. The training loop uses no external training examples or human-written answer labels. On the primary eleven-benchmark suite, A-RSI raises the performance average from 57.77 to 61.05 with 800 fresh tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36991

SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation

Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazangirler

原文摘要

Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk dependencies, and provide incomplete evidence for multi-hop reasoning. We propose SpectRAG, a spectral graph-augmented retrieval framework that combines hybrid candidate seeding, weighted chunk graph construction, graph-based expansion, spectral relevance propagation, and token-budgeted context selection. Document chunks are represented by dense semantic embeddings and graph-spectral coordinates derived from a weighted chunk graph whose edges encode semantic similarity, document adjacency, section hierarchy, shared entities, citation links, and similarity between LLM-generated utility questions. At query time, SpectRAG builds a high-recall seed set using exact inner-product search and hybrid relevance signals, expands it over the chunk graph, re-scores candidates using graph proximity and spectral information, and assembles the final context under a fixed token budget. The goal is not merely to retrieve individually similar chunks, but to construct a context that is relevant, diverse, structurally connected, and sufficient for grounded reasoning. Experiments on MultiHopRAG, UltraDomain, and long-document question-answering settings show that SpectRAG improves broad evidence recovery and achieves competitive generation quality against dense, hybrid, HyDE, LightRAG, and NaiveRAG baselines. The results further indicate that graph-spectral structure is particularly useful for inference-oriented and cross-document retrieval, while highlighting trade-offs in early precision, computational cost, and domain-dependent performance.

cs.AI · cs.CL · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38566

Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation

Chengsheng Zhang, Wenshen Xu, Yuchuan Wu, Zhiyuan Yu, Junfeng Fang, Tianlong Wang, Bingxue Qiu, Yongbin Li 等 9 位作者

原文摘要

Rubric-based reinforcement learning (RL) offers interpretable, fine-grained supervision for aligning large language models (LLMs) on open-ended generation tasks. However, static rubric criteria may become saturated or remain beyond the policy's exploration, rendering the reward signals insufficiently discriminative. While recent efforts seek to guide sampling exploration or evolve rubrics, they fail to explicitly factor in how rubric difficulty should track the evolving policy's capabilities, resulting in a persistent mismatch between the optimization objective and the policy's current capability frontier. In this paper, we propose \textbf{Co}-Evolving Policy and Rubric via \textbf{C}apability \textbf{A}wareness (\textbf{CoCA}), a closed-loop framework that jointly adapts the rubric and policy through criterion-level diagnosis. Specifically, CoCA contrasts query-only and rubric-guided rollouts to characterize each criterion relative to the current policy, recalibrates criteria with mismatched difficulty, and identifies guidance-revealed capability gaps for frontier-based learning. Based on this insight, CoCA either expands rubric-conditioned frontiers through guided optimization or transfers qualified gains through on-policy self-distillation. As the policy updates, CoCA improves the capability diagnosis and enables more reliable distillation, thereby completing the co-evolution loop. Extensive experiments across diverse benchmarks and LLMs demonstrate that CoCA consistently improves performance over rubric-based RL methods. Moreover, CoCA promotes the internalization of guidance-revealed capabilities into query-only behavior while mitigating capability degradation.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.30448

Proba: A High-Performance, Low-Traffic Probabilistic Spatial Memory Streaming Prefetcher

Yinting Huang, Jacky Wong, Sam Ainsworth

原文摘要

Spatial Memory Streaming (SMS) prefetchers exploit recurring spatial access patterns across memory regions to predict future accesses. Despite their effectiveness, existing SMS-based designs suffer from coarse control over aggressiveness and limited adaptability to dynamic program behavior and historical patterns. In this work, we present Proba, a feedback-directed SMS-based prefetcher that integrates probabilistic pattern updates, marginal accuracy decision-making, and pattern accumulation over several trigger features to achieve fine-grained accuracy-coverage trade-offs. When accuracy deteriorates, Proba moderates its aggressiveness to prioritize accurate prefetches; conversely, when accuracy rises, it expands its coverage. Proba achieves higher speedups than any other SMS-based prefetcher while being vastly more efficient in DRAM traffic. This culminates in a large performance gap between Proba and other techniques in multicore and DRAM-constrained scenarios without harming single-threaded throughput.

cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.16132

UniSGR-V2: Stepwise Target-Side Feature Anticipation and Crossing for Generative Recommendation

Jun Yang, Jiasi Chen, Jiawei Sun, Ziyue Guo, Jianan Yan, Tao Luo

原文摘要

Semantic-ID-based generative recommendation unifies retrieval and ranking through autoregressive decoding but differs structurally from discriminative models, which can directly access rich target-item side features. The attributes are compressed into a finite codebook during quantization, while the target item remains undetermined during decoding and its features cannot be looked up. This target-side feature vacuum weakens generation at each semantic-ID level through high conditional entropy and cascading errors, and final ranking through missing target-side feature crossing. Existing methods interact with candidate representations or generate discrete attribute tokens, but none reconstructs a continuous target-side representation inside decoding to support both stepwise generation and ranking. We propose TacGR (Stepwise Target-Side Feature Anticipation and Crossing for Generative Recommendation). Before decoding each codeword, TacGR anticipates a continuous target-side feature vector and crosses it with the semantic prefix and user behavior sequence inside the decoder. The crossed representation conditions current-level generation and is directly used for ranking. Continuous-vector regression risks a learnable target collapsing with its prediction and prediction noise propagating into generation through attention. TacGR addresses these challenges with a semantic-anchoring auxiliary tower and a unidirectional visibility mask, respectively. For extremely long industrial behavior histories, it introduces gated convolutional denoising to suppress noise and adapts the pyramid memory funnel to reduce inference cost. Offline experiments on a large-scale Lazada dataset show significant gains over OneRec, UniRec, and UniSGR. Online A/B testing improves IPV, Order, and GMV by 0.79%, 5.55%, and 3.09%, respectively.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38561

Persona Learning from Feedback for Personalized AI Assistants

Yiran Shen, Yu Xia, Liuyi Yao, Prithviraj Ammanabrolu

原文摘要

Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts. Existing work elicits assistant personas through persona prompting or finetuning on persona-conditioned generations. However, persona descriptions alone do not identify what to change or preserve in a particular response, or which behaviors suit the current request. We introduce $\textit{Persona Learning from Feedback (PLF)}$, a framework that learns reusable, preference-grounded assistant personas as independent LoRA adapters on a shared frozen backbone. During training, a frozen self-teacher conditions on persona specifications and response-specific feedback to provide token-level supervision on each adapter's own generated prefixes. A feedback gate focuses corrective updates on responses judged to need improvement. At deployment, a supervised router uses the request or dialogue to select a single adapter or a fixed composition, without user-specific finetuning. We evaluate PLF on single-turn personalization with model-generated critiques and multi-turn tutoring with simulated students' reactions. Across both settings, PLF improves model-judged preference fit over fixed-persona policies and strong baselines including persona prompting and persona distillation, demonstrating how feedback-trained behaviors can be reused for adaptive assistant personalization without degrading general capabilities.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38559

A goodness of fit approach to select the optimal visit sequence for nonparametric data synthesis

R{é}my Chapelle, Bruno Falissard, Mohammed Sedki

原文摘要

Synthetic data are a promising way to maintain privacy while disseminating research data, thereby enabling compliance with the open science principles. Popular methods for generating synthetic data include sequential synthesis, where each variable is generated conditionally on the preceding ones in a given order. This order, also called the visit sequence of the synthesizer, is known to affect the quality of synthetic data. This raises the question of the criteria that should guide its choice. In this work, we present a novel method to perform such selection based on a goodness of fit criterion, and show that it outperforms alternative structure-based methods, both in terms of synthesis quality and time complexity. The proposed method also has the advantage of being applicable to any type of data and any class of conditional distribution models.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38558

REVBRAIN: Real-time Probabilistic EEG Forecasting Using Residual Vector Quantization

Hanna Pankka, Jaakko Lehtinen, Timo Roine

原文摘要

Real-time forecasting of resting-state EEG signals is required by applications like brain-state-dependent stimulation, where computer generated actions are coupled with ongoing neural oscillations. Recently, the deep learning model WaveNet was proposed for the forecasting task. It shows superior accuracy compared to the prevailing method, the linear autoregressive (AR) model, and provides a built-in uncertainty measure due to its probabilistic modeling framework. However, inference using WaveNet is too slow for real-time use due to its sample-by-sample autoregressive operation: a single forecast requires evaluating the model tens or hundreds of times depending on the length of the prediction window. In this paper, we present REVBRAIN, a probabilistic deep learning method that produces forecasts in real time by generating the forecast over the whole prediction horizon at once. This is achieved by tokenizing the output space using residual vector quantization (RVQ) and generating forecasts over the items in the tokenized space. We tested REVBRAIN for forecasting 200 ms of EEG time series in the alpha-frequency band (8-13 Hz) and compared our results against WaveNet model. We found that REVBRAIN achieved real-time inference on a laptop GPU and an over $50\times$ speedup compared to WaveNet, while reaching superior prediction accuracy. By achieving real-time inference speed, REVBRAIN enables incorporating accurate and probabilistic EEG forecasting into BCI applications, opening up new ways for investigating the functioning of the human brain.

cs.LG · eess.SP · q-bio.NC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38557

A Minimally Informed Black-Box Fake-Report Attack on DRL Traffic-Signal Control

Amro Saleh, Loukas Lazos, Mohammad J. Abdel-Rahman

原文摘要

Deep reinforcement learning (DRL) traffic-signal controllers may use vehicle-to-infrastructure (V2I) reports, exposing their perception layer to false-data injection. Existing demonstrations typically assume either white-box access to the controller's weights or full observability of the traffic state. We study the impact of a weaker and more realistic adversary who has no access to the RL model and whose traffic observations are limited to her own approach. This black-box, minimally informed attacker trains an imitation surrogate of the controller. She then crafts bounded fake reports, restricted to inflating vehicle counts on her own approach, that transfer to the real controller. We demonstrate that despite the loss of accuracy relative to an attacker who can observe the entire state and action space, this limited attacker can significantly increase the average waiting time for other approaches while barely changing the waiting time on her own approach, i.e. externalizing the added delay onto the other approaches. Because the only realizable move is to inflate one's own reported queue, we find that a zero-knowledge attacker that simply reports the maximum feasible queue is as damaging as the surrogate-based one, while an unstructured random inflation is not: the surrogate is not required to reproduce the degradation, and the exposed vulnerability is the V2I sensing channel itself. The surrogate's role is directional control, selecting a disruptive or a selfish objective at the same budget. The attack persists under +/-20% uniform demand variation. Finally, on a common per-lane budget we place the attacker on a knowledge ladder against white-box adversaries, and find the black-box surrogate matches a realizable white-box attacker that uses the victim's own gradients; only abandoning realizability raises the damage further.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38551

PT$^3$: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representation

Ziyang Liu, Kieren Yu, Xiao Yang, Xin Yang, Kaishun Wu

原文摘要

Multi-source millimeter-wave (mmWave) observations offer an opportunity to learn human representations reusable across sensing tasks. However, sparse detections and multipath effects make these observations unstable, challenging existing point cloud pretraining methods. We propose PT$^3$, a prototype-guided self-supervised pretraining framework for mmWave human point clouds. PT$^3$ represents local states in spatial regions as sparse compositions of shared prototypes and learns their temporal evolution through autoregressive prediction. Observation consistency further stabilizes representations under radar perturbations. After pretraining on unlabeled sequences from multiple sources, the same frozen encoder supports action classification, dense point generation, joint pose estimation, and future motion prediction on datasets not used for pretraining. Across these tasks, PT$^3$ outperforms the compared pretraining baselines and achieves competitive or superior performance to task-specific models.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38547

Detecting Fine-Grained Differences between Image Datasets

Leander Girrbach, Alexander von Recum, Kirill Bykov, Zeynep Akata

原文摘要

Detecting whether and in particular how two data distributions differ is a fundamental statistical problem. For example, we might be interested in which concepts (expressed in natural language) differ between two classes, the outputs of different generative models, or the same model with different prompt specifications. When working with large and complex image datasets, we intuitively think that first selecting concepts from a broad list using fine-grained patch embeddings, and then optimizing the concepts to better fit the data is an effective workflow. However, prior work instead uses MLLMs to propose concepts and image-level embeddings to select them. Therefore, we systematically compare these techniques and find that selecting concepts from broad lists can replace MLLM-proposals at obviously lower cost. MLLM inference can then be spent on optimizing selected concepts instead to achieve substantial improvements. Additionally, by designing a new benchmark that focuses on low-prevalence and multi-concept distinctions, we find that selecting nonredundant concepts instead of only the most distinguishing concepts matters, and we introduce techniques for how to effectively do this. Finally, we show how our methods address important problems like detecting spurious correlations and biases. Overall, our work presents a fundamental perspective shift on how we analyze interpretable distributional differences between datasets.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38546

Implicit Minor Detection from Multi-Turn Dialogue in High-Risk AI Interactions: A Constrained Self-Evolving LLM Harness

Xiaohan Zhang, Ying Zhao, Ruilin Guo, Xuanyuan Yu, Kaibo Huang, Yukun Wei, Zhongliang Yang, Linna Zhou

原文摘要

In high-risk text interactions, a system may need to estimate whether the current speaker is likely to be a minor before applying age-conditioned safeguards. Many text-based dialogue systems lack strong identity signals such as account information, verified identity, facial data, or device data, and must rely on weak cues that emerge across multiple turns. We formulate implicit minor detection under weak identity information as a high-risk user-attribute inference task and propose a constrained framework comprising a large language model, a Harness, and a Maker-Checker protocol. The framework controls when inference is invoked, requires structured dialogue-linked evidence, and subjects validation-selected Harness revisions to version-level review. On a controlled Chinese benchmark comprising 8,328 multi-turn dialogues, our method improves average precision and minor-class F1 by 7.60 and 6.37 percentage points, respectively, over direct inference using the same LLM family.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.14222

Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents

Afshan Hashmi

原文摘要

Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win rate. Concurrently, the PageIndex framework reported 98.7% accuracy on FinanceBench through purely reasoning-based retrieval. This paper extends their work by: (i) implementing and evaluating three retrieval configurations: Vector RAG, Tree Reasoning, and the proposed Adaptive Hybrid Retrieval (AHR), on a small controlled corpus of financial, legal, and medical documents; (ii) introducing a four-tier query complexity benchmark; and (iii) employing LLM-as-judge evaluation with GPT-4o-mini. Experiments reveal that Tree Reasoning achieves the highest overall score (0.900), but no single paradigm dominates across all tiers: AHR scores highest on cross-reference queries (0.850), all three methods tie on multi-section queries (0.929), and Vector RAG scores highest on the single multi-document query (0.900). Vector RAG has the lowest mean latency (1.61 s against 3.40 s for Tree Reasoning). On the first 50 publicly released FinanceBench questions, using the evidence snippets supplied with the benchmark as the retrieval corpus, Tree Reasoning scores 0.938, Hybrid AHR 0.901, and Vector RAG 0.821. Because the configurations also differ in document access, generation prompts and output length limits, these differences cannot be attributed to retrieval architecture alone. In these preliminary results the adaptive router does not outperform fixed tree reasoning overall (0.845 vs. 0.900); they motivate a larger evaluation of when query-based routing helps, rather than establishing its benefit.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38545

TSM diff: A new Parallel-Tree-Traversal Algorithm for the Comparison of Music Score Files

Xiaobo Wang, Florent Jacquemard

原文摘要

Music score files are more difficult to compare than their text-based equivalents, as their content is more complex and organised into hierarchical structures. This explains the lack of tools for processing music scores similar to the widely used old Unix diff command. We propose a new algorithm and tool for comparing digital music scores in various encodings, such as MusicXML or MEI, based on a graph-structured abstract representation called Tree Score Model (TSM). Given two scores, after conversion into TSM, our procedure calculates jointly: A list of differences, localised by time positions in the input scores; A time distance, cumulated duration of time-spans where scores differ; An edit distance, called surface distance, based on notational attributes not related to time. The two later measures are normalised and combined into a similarity distance between scores. Our procedure has been implemented in C++ and is available as a Python module. Our first experiments have shown a very good efficiency even on challenging data. As a proof of concept, we propose two demos based on different versions of some Mozart's piano sonata, and transcriptions of monophonic soli on the same jazz standards by different performers. https://tsm-diff-lbd-7a7e2a.gitlab.io/demo.html

cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38543

The State of the Practice in Privacy Impact Assessments: Understanding the Professionals' Perspectives, Experiences, and Current Procedures

Samuel Wairimu, Leonardo Horn Iwaya, Ala Sarah Alaqra

原文摘要

Organisations frequently utilise Privacy Impact Assessments (PIAs), Data Protection Impact Assessments (DPIAs), or even Fundamental Rights Impact Assessments (FRIAs) to identify and evaluate potential risks and possible infringements of fundamental rights. While the adoption of PIAs and DPIAs has grown significantly in recent years, robust scientific evidence regarding their operational challenges, implementation strategies, and tangible benefits remains scarce. In particular, empirical research conducted post-enactment of the General Data Protection Regulation (GDPR) is notably limited -- especially studies that directly interview professionals about their PIA/DPIA practices or their engagement with FRIAs. To do so, in this paper we leveraged semi-structured interviews to elicit privacy professionals' perspectives on PIA/DPIA activities and analysed the responses using reflexive thematic analysis. As a result, this work provides a comprehensive thematic framework for the field, offering a rich and thick description of professionals' views and experiences. In total, 26 participants from 17 countries were interviewed, revealing how they plan and conduct PIAs/DPIAs, including how they assess trade-offs, the benefits and challenges they perceive, and how they view the interplay between PIAs/DPIAs and the EU AI Act. Among the main findings were low adherence to established DPIA methodologies; differences and similarities between PIAs and DPIAs; a perceived neglect of data subjects' interests during DPIA processes; discussions on building FRIAs on top of DPIAs; and the potential for holistic impact assessments, though accompanied by concerns regarding assessment fatigue. Thus, this study informs privacy professionals about real-world challenges and experiences of PIA/DPIA implementation, and guides researchers toward future research directions.

cs.CY · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38544

An Alignment Benchmark for Enterprise Agents on Era by Eon

Hai Sadon, Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary

原文摘要

AI agents are widely used in enterprises to access business systems and act on them in pursuit of a goal. However, fulfilling a user's request can cause harm. Era by Eon is a product that creates a digital twin of a company by simulating its business systems and data. Its simulators implement the programming interfaces of real products. Our benchmark uses ten of these systems, including Salesforce, Zendesk, Jira and Slack. We tested whether agents would carry out harmful business requests or trust misleading information in company records. We ran 19 models on 41 tasks three times, for 2,337 runs. Of the 2,304 runs that produced an answer, 918 (40%) contained a violation. The most common were false claims about actions or records (290 runs), following planted instructions (266) and disclosing sensitive data to the wrong audience (249). Every attempted change was recorded and blocked before it took effect. Misleading Slack messages caused 16 models to report an incorrect ticket status in 47 of 57 runs. No model was free of violations. The four best models violated in 22 to 24% of their runs. Yet one of them, Nova Pro, did the task correctly in only 30 runs.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38536

Influence of Agent Number and Behavior on Users' Psychological Responses in VR Evacuation Training

Naoki Matsumura, Kensuke Sugihara, Tomoko Yonezawa

原文摘要

This study aims to build effective drill software by combining a virtual simulation of a disaster with multiple agents capable of expressing emotions. We evaluated how the number of agents and their emotional and behavioral actions during evacuation influence users in a virtual space. The results showed that users tended to act more confidently when many agents evacuated with them, and that the evacuation route chosen by the agents influenced the users' decision-making. These findings indicate that users' evacuation behavior is shaped not only by the environment itself but also by the collective behavior of surrounding agents, underscoring the need to consider how agent behavior affects users' psychological states during training.

cs.HC · cs.MM · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38535

On the Complexity of Computing with p-adic Lattices

Pierre Fromonot, Mercedes Haiech, Tristan Vaccon

原文摘要

We study the complexity of two fundamental problems attached to p-adic lattices: computing an N-orthogonal basis, and deciding whether a given basis is N-orthogonal. When the norm is supplied through an explicit diagonal representation, both problems are polynomial. However, in the black-box model, where the ultrametric norm N is fixed and only accessible through an evaluation oracle, we prove that both problems require $Ω$(p^{v-1} ) queries in the worst case, where v $\le$ n is the largest multiplicity of a commensurability class of N and n is the dimension of the ambient vector space. We then analyse the optimality of these bounds by providing explicit algorithms. Our results answer formally an open question of Zhang, Deng and Wang and refine the recent results of Duan and Wu by providing pointwise query bounds depending on the norm's structure, in addition to uniform bounds.

cs.SC · math.NT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.11846

SheafStain: Sheaf-Theoretic Schrödinger Bridge for Spatially and Biologically Coherent Virtual Staining

Hyeongyeol Lim, Hongjun Yoon, Eunjin Jang, Daeky Jeong, Won June Cho, Hwamin Lee

原文摘要

Current virtual staining approaches offer the potential for time- and cost-efficient biomarker quantification in cancer diagnostics and prognostics. However, patch-wise inference for gigapixel whole-slide images fails to maintain spatial continuity, yielding artifacts that cause catastrophic mismatches with ground-truth images. Although pathology Vision Foundation Models (VFMs) offer rich representations, their self-attention causes varying global contexts to produce inconsistent embeddings for the same physical region. We formalize and validate this "context contamination" as a sheaf-theoretic problem where these embeddings form a presheaf whose sections disagree on overlaps, so no global section restricts to them. To address this, we propose SheafStain, a new approach that reinterprets VFM features as sheaf-like sections for spatially and biologically coherent virtual staining. Specifically, SheafStain integrates class and patch tokens into a Schrödinger Bridge framework as sheaf-like sections. While the class token anchors biological consistency, patch tokens form a per-position spatial map. A feature space from a single VFM encoder pretrained on Hematoxylin \& Eosin and Immunohistochemistry supervises both input conditioning and output stain alignment. Departing from prior work that evaluates on isolated $256 \times 256$ patches and either random-crops or resizes the $1024 \times 1024$ ground truth, we translate at $256 \times 256$ and evaluate on the stitched $1024 \times 1024$ outputs across HER2, ER, PR, and Ki-67. SheafStain demonstrates promising results against six prior methods while mitigating patch-boundary stitching artifacts. Code is available at https://github.com/deepnoid-ai/SheafStain.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.02982

oRANS: Online optimisation of RANS machine learning models with embedded high-fidelity data generation

Daniel Dehtyriov, Jonathan F. MacArt, Justin Sirignano

原文摘要

Deep learning (DL) has shown promise for flow simulations, but progress is constrained by the scarcity of high-fidelity training data, which is costly to generate and limited to few flow conditions. Closures trained offline on such data tend to overfit and fail to generalise to new regimes. We introduce an online optimisation framework for DL-based Reynolds-averaged Navier-Stokes (RANS) closures. Training data is generated by a simulation at direct numerical simulation (DNS) resolution embedded in a subdomain of the RANS domain. The RANS solution supplies boundary conditions to the embedded simulation, which provides the mean velocity and turbulence statistics used to update the closure, which thereby adapts to the target flow without precomputed datasets. The approach is developed on the stochastically forced Burgers equation and on turbulent channel flow at $Re_τ=180$, 270, 395 and 590 with embedded domain lengths $1\leq L_0/L\leq 8$, and is then applied to spanwise-rotating channel flow at $Ro_b=0.15$ and $0.5$, a flow in which the Coriolis force vanishes from the equations of a linear eddy-viscosity closure. Online-optimised RANS models outperform offline-trained and literature-calibrated closures with modest embedded subdomains, and in the rotating channel recover the rotation-induced asymmetry from non-rotating inflow turbulence and a rotation-blind closure. The learned coefficients are interpretable, recovering near-wall damping and, under rotation, the collapse of the eddy viscosity on the stabilised side. Performance degrades when boundary contamination dominates or domains are too short to capture low-wavenumber modes. This framework provides a route to data-adaptive machine learning closures without large precomputed training datasets.

physics.flu-dyn · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36910

Nothing Left Behind: Embedding Retrieval and Language Model Screening for High Recall Evidence Search

Giuliano Martinelli, Abelardo Carlos Martinez Lorenzo, Satvik Garg, Linxi Wang, Riccardo Orlando, Piriyakorn Piriyatamwong, Samuel Paul Fraiberger

原文摘要

AI systems that ground their answers from retrieved documents usually need only a few relevant passages, but applications such as systematic reviews and legal discovery need nearly all of them, because their conclusions rest on the full body of evidence. These applications have traditionally searched with curated taxonomies, which can only find what their vocabulary describes. We compare taxonomy-based retrieval with an alternative neural retrieval based on sentence embeddings and followed by language model screening in ImpactAI, an evidence synthesis application built on 7,354 randomized trials. Measured against the studies included in 29 systematic reviews, the share of studies found rises from 45% to 85%, and the screening model agrees with human annotators as well as annotators agree with each other. This gain comes at a cost in speed: at the median, retrieving and screening evidence for a query takes 77 seconds, against 6 seconds for taxonomy retrieval. The results suggest finding evidence with embeddings, organizing it with taxonomy labels, and setting how many candidates to screen according to the time available for each query.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.06600

Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning

Zhuoyuan Hao, Zhuo Li, Wu Li, Fangming Liu, Min Zhang, Jing Li

原文摘要

Recent work improves reasoning in large reasoning models (LRMs) by test-time scaling through self-consistency and parallel thinking, adding generic "thinking tokens", or presenting the question twice, as in re-reading (RE2). However, these approaches either inject task-agnostic tokens or mandate heuristics that do not explain, and often ignore, the spontaneous repetition that many LRMs exhibit at the head of their long chain-of-thought (CoT). In this work, we analyze and harness the model's tendency to restate the question, dubbed Echo of Prompt (EOP), as a front-loaded, compute-shaping mechanism, which can be viewed as self-generated prompt repetition inside the reasoning trace rather than in the input. Specifically, we formalize its probabilistic cost by casting echo removal as rejection-based conditioning, and define the Echo Likelihood Gap $Δ\mathcal{L}$ as a computable proxy linking early repetition to likelihood gains and downstream accuracy. We find that (1) in a causal intervention, reinserting an echo into failed GSM8K traces raises exact match by 7.9-10.4 points for two reasoning models but not for a non-reasoning base model; and (2) in length- and suffix-controlled likelihood analyses and layer-wise attention studies conducted to show that EOP's benefits go beyond verbosity, EOP increases answer to answer-prefix attention in middle layers, consistent with an attention refocusing mechanism. Building on these findings, we develop Echo-Distilled SFT (ED-SFT) to instill an "echo-then-reason" pattern through supervised finetuning, and training-free Echoic Prompting (EP) to re-ground the model mid-trace. We evaluate on GSM8K, MathQA, Hendrycks-MATH, AIME24, and MATH-500 under identical decoding settings and budgets, and find consistent gains over baselines, including thinking-token insertion. Our code is publicly released at https://github.com/hhh2210/echoes-as-anchors.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38532

From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

Nouar AlDahoul, Yasir Zaki

原文摘要

LLMs increasingly fact-check online content with the poster's identity in view. However, it remains unclear which post-training changes how much a model's truth judgement depends on the poster's social class, and how such a change happens inside the model. This paper investigates job-based doubt, i.e., judging a claim false more often when the poster has a lower-status job, using fact-checked claims with randomised poster profiles in base and post-trained checkpoints of six model families. Our results reveal that: 1) post-training creates such doubt only with the open Tülu-3 recipe (OLMo-2 32B, Tülu-3 70B), not with Meta's, Alibaba's or Mistral's; the effect is under one percentage point but statistically reliable, exceeding training drift and replicating on independent claim sets; 2) in OLMo-2 32B, the model does not start noticing the poster's job more, but starts interpreting it differently: a lower-status job pushes the base model toward "true" and the post-trained model toward "false"; and 3) this flip is carried by a single residual-stream direction and happens at supervised fine-tuning. The mechanism was confirmed on 400 new claims with pre-specified predictions. None of seven deployed commercial models doubts lower-status posters more. Our work underscores the need to audit speaker bias per training recipe.

cs.AI · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.18564

Observation Quality in DSM-Assisted Aerial Localization: A Benchmark and Base-Anchored Uncertainty Calibration

Pengyu Yin, Jie Pan, Junxiang Tan, Mengqi Fu, Kun Cheng, Yifan Liu

原文摘要

Aerial map matching provides position observations for navigation, but a position error alone does not determine how an observation should be weighted. We define five benchmark tasks: position availability and agreement, grouped error structure, predictive uncertainty, controlled updates, and temporal accumulation. We use digital-surface-model-assisted localization to test whether base-anchored uncertainty calibration improves the weighting of unchanged position estimates. The method combines propagated image and map sensitivities with the second moment of a compact configuration subset relative to the reported position. Scale is fitted using separate position references without local surface-height ground truth. Thirteen covariance models are evaluated on two held-out query sets from locations represented in the calibration data. Using reference residuals, we compare the method with a constant full-matrix baseline. With all localization failures included, the method reduces the normalized position-update risk, averaged equally across locations, by 7.70% on 728 conditions and 5.46% on a separate 142 conditions under an independent prior. On the primary set, the equal-location average negative log likelihood on reference residuals improves by 2.571 nat. At these seen locations, exploratory base-only quality calibration and conditional-addition controls leave the incremental update benefit of configuration disagreement unresolved. Navigation benefit and real temporal accumulation remain untested.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38530

From the Superderivative to a Relative-Gradient Edge Operator

Alejandro Garnung Menéndez

原文摘要

First-derivative edge detectors such as Sobel, Prewitt, Roberts and Scharr measure absolute grey-level differences. We revisit the log-gradient magnitude, a relative-gradient edge operator, and motivate it by analogy with the superderivative, a multiplicative derivative in which the independent variable is perturbed multiplicatively rather than additively. In one and two dimensions the logarithm of the superderivative is a radial logarithmic derivative; its local, origin-free, isotropic analogue is the magnitude of the logarithmic gradient. The resulting operator measures relative rather than absolute change, giving an edge-strength map that is invariant under global intensity rescaling. We present the theory, show how the operator can be implemented in two steps---a classical gradient kernel plus a pointwise division---and compare it with standard first-derivative filters on synthetic images with ground-truth edges and on the official BSDS500 benchmark. We also study a parametric family that interpolates between the absolute gradient and the log-gradient; empirically, the best members are small intermediate exponents, which edge the classical kernels by a small but statistically detectable margin in the per-image metric and, with the same Gaussian smoothing as the single-$σ$ Canny, match it in ODS and lead it in OIS and AP, while the tuned Canny remains ahead in ODS. The single-threshold margin over the kernels does not replicate on the held-out test split, and the fully relative endpoint is never the best member, its ranking depending on the edge-map normalisation. The contribution is the construction and the invariance it buys, not a new state of the art.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36888

Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learning

Martín de Frutos, Baptiste Corban, Claire Bizon Monroc, Ana Bušić, Donatien Dubuc, Jiamin Zhud, Esteban Ferrer

原文摘要

Existing noise mitigation strategies for wind farms usually consist in reducing turbines power output, without accounting for the wake interactions between them and the noise emission directivity. This leads to over-conservative policies and unexploited wind power. Yet, turbine yaw can simultaneously affect wake interactions and the direction of noise emission, offering an additional degree of freedom for farm-level noise control. We therefore propose Noise Steering, a model-free reinforcement learning (RL) strategy that jointly controls turbine yaw angles and power setpoints to maximise farm power while satisfying a local noise constraint in a defined region. To enable training at a reduced computational cost, a low-fidelity acoustic model is coupled with the steady-state FLORIS simulator. The RL agent effectively learns how to redirect wakes and noise directivity away from the protected region while redistributing power across the farm. On a six-turbine test farm, the policy satisfies the 40 dB noise constraint throughout the full range of turbulent winds, with an average power deficit of only 2% relative to greedy unimpeded control, and up to 7.7% at high wind speeds. In comparison, the industry-standard noise-reduced operation (NRO) baseline here generates an average power loss of 17%. When deployed in the higher-fidelity FASTFarm simulator, the policy largely retains its performance under steady and turbulent inflow, despite differences in simulation fidelity. These results demonstrate the potential of combining yaw control and power derating through RL to improve the power-noise trade-off in wind farm operation.

cs.AI · eess.SY · physics.ao-ph · physics.flu-dyn

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38526

Value Probes: Learned Value Functions for Beam-Search Red Teaming

Jonathan F. Jao, Andrew Kyle Lampinen

原文摘要

Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors. These audits implicitly search a tree of possible conversation pathways: at each turn an auditor model decides which conversation to continue, and an LLM judge scores the dialogue. We emphasize that this auditing procedure is a Markov decision process, where states are the conversation history, actions are candidate responses, and rewards are judge scores for the target behavior. By adopting this perspective, we introduce two major improvements to auditing. First, we propose adopting beam search for the audit rather than relying on the auditor alone. We then interpret the problem of finding states that are likely to lead to problematic behavior as value estimation. Surprisingly, we show that this value function can be estimated by linear probing from the target model's activations to predict discounted future rewards - a method we term "Value Probes." By using Value Probes as a heuristic in our beam-search audit, we are able to substantially improve auditing success. Across 18 target behaviors and 3 scales of models, our approach raises peak audit scores by roughly 50% compared to (token-matched) standard auditing approaches. Furthermore, we show that Value Probes can be fit using off-policy data from smaller models. We also ablate individual components, and show that our method offers a comparably-performant and more efficient alternative to more expensive language model follow-ups. We hope these methods will improve language model auditing and lead to safer models.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38525

Dimension-free exponential entropy quotients over $\mathbb{F}_2$

Josiah Park

原文摘要

Let $X$ be a random vector in $\mathbb{F}_2^m$, and let $X'$ be an independent copy. We prove that, for every $\varepsilon>0$, there is a subspace $G$ with $\dim G\le 2^{320(1+\varepsilon)/\varepsilon}H(X)$ such that $H(q_GX)\le(1+\varepsilon)(H(q_GX+q_GX')-H(q_GX))$. In particular, the quotient entropy is at most $(1+\varepsilon)(H(X+X')-H(X))$. The coefficient is independent of the ambient dimension, and its exponential order in $1/\varepsilon$ is necessary. The structural result is a logarithmic rigidity estimate for finite weighted families of laws with averaged subspace entropy sparsity. A common variational quotient controls both a family and its convolution family without decreasing the original family's normalized mean entropy defect. Posterior families preserve averaged sparsity, and a fresh-index argument combines a local-to-global estimate with the entropic Marton theorem to increase the defect ratio at a fixed multiplicative sparsity cost. We also obtain two-input almost-additivity and concentration of moderate-doubling sets on subspace cosets at the same exponential scale. The constants are not optimized.

cs.IT · math.CO · math.PR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.16510

Simplified Algorithms and Improved Bounds for Motion Planning

Sarita de Berg, Joachim Gudmundsson, Peter Kramer, Christian Rieck, Sampson Wong

原文摘要

We investigate coordinated motion planning (CMP) for unit square robots in the plane under the $L_1$ metric. Given two arrangements of $k$ robots, we seek a movement schedule minimizing one of three objectives: the Min-Sum objective (sum of distances), the Min-Makespan objective (latest time of arrival) and the Min-Exposure objective (a new objective). For Min-Sum and Min-Makespan, we provide a simplified approach and improved bounds, compared to Eiben, Ganian and Kanj (SoCG 2023). To this end, we partition the configuration space based on the relative ordering of the robots. This leads to a simple and efficient framework to discretize the search space. Our results extend to several settings in the plane, including convex robots in convex domains and vertex robots in rectangular grids. Finally, we apply our results to the new Min-Exposure objective. Given a set of polygonal regions that provide cover, the task is to find a schedule with minimal elapsed time during which at least one robot is not fully covered. We give an $\mathcal{O}(n^4\log n)$ time algorithm that computes exposure-minimal schedules for $k=2$ robots, and an XP algorithm for arbitrary $k$.

cs.CG

查看论文
arXiv ↗PDF ↗